© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82439
    Prev
    Next
    INDEX
    Explanations

    leaked documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DPA
    -0.79
    ‌لار
    -0.75
    监控
    -0.71
    étit
    -0.71
     fore
    -0.69
    ($_
    -0.69
     rooftops
    -0.69
     per
    -0.68
     immun
    -0.67
    잊
    -0.66
    POSITIVE LOGITS
     documents
    1.27
    Papers
    1.14
     Papers
    1.09
     dump
    1.07
     papers
    1.04
    documents
    1.03
     Panama
    1.02
     documentos
    1.02
     Documents
    1.00
     документов
    1.00
    Activations Density 0.020%

    No Known Activations